INDEX

Explanations

terminology related to business models

oai_token-act-pair · gpt-3.5-turbo

references to different business models

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

azar

-0.93

hedon

-0.79

èª

-0.79

 NOTICE

-0.74

des

-0.73

olulu

-0.72

minster

-0.72

ãĥĥãĥĪ

-0.71

endo

-0.70

ugu

-0.70

POSITIVE LOGITS

 model

0.72

model

0.71

 organism

0.70

 exemplary

0.66

 Model

0.64

 Blueprint

0.64

 loader

0.64

 playbook

0.63

 backbone

0.63

 Approach

0.63

Activations Density 0.018%

terminology related to business models

references to different business models

No Comments

No Known Activations